EDDense-Net: Fully Dense Encoder Decoder Network for Joint Segmentation of Optic Cup and Disc

TL;DR

The paper introduces EDDense-Net, a dense encoder-decoder network designed for joint segmentation of optic cup and disc, improving glaucoma diagnosis accuracy and efficiency through advanced deep learning techniques.

Contribution

It proposes a novel dense encoder-decoder architecture with grouped convolutions and dice loss for improved joint segmentation of optic cup and disc.

Findings

Outperforms existing methods in accuracy and efficiency

Effective handling of class imbalance with dice pixel classification

Validated on two public datasets

Abstract

Glaucoma is an eye disease that causes damage to the optic nerve, which can lead to visual loss and permanent blindness. Early glaucoma detection is therefore critical in order to avoid permanent blindness. The estimation of the cup-to-disc ratio (CDR) during an examination of the optical disc (OD) is used for the diagnosis of glaucoma. In this paper, we present the EDDense-Net segmentation network for the joint segmentation of OC and OD. The encoder and decoder in this network are made up of dense blocks with a grouped convolutional layer in each block, allowing the network to acquire and convey spatial information from the image while simultaneously reducing the network's complexity. To reduce spatial information loss, the optimal number of filters in all convolution layers were utilised. In semantic segmentation, dice pixel classification is employed in the decoder to alleviate the problem of class imbalance. The proposed network was evaluated on two publicly available datasets where it outperformed existing state-of-the-art methods in terms of accuracy and efficiency. For the diagnosis and analysis of glaucoma, this method can be used as a second opinion system to assist medical ophthalmologists.